ABSTRACT
This paper proposes a novel approach to single image super-resolution. First, an image up-sampling scheme is proposed which takes the advantages of both bilateral filtering and mean shift image segmentation. Then we use a shock filter to enhance strong edges in the initial up-sampling result and obtain an intermediate high-resolution image. Finally, we enforce a reconstruction constraint on the high-resolution image so that fine details can be inferred by back projection. Since strong edges in the intermediate result are enhanced, ringing artifacts can be suppressed in the back projection step. We compare our algorithm with several state-of-the-art image super-resolution algorithms. Qualitative and quantitative experimental results demonstrate that our approach performs the best.
- J. Allebac and P. W. Wong. Edge-directed interpolation. In Proc. ICIP, 1996.Google ScholarCross Ref
- S. Baker and T. Kanade. Limits on super-resolution and how to break them. In Proc. CVPR, 2000.Google ScholarCross Ref
- D. Comaniciu and P. Meer. Mean shift: a robust approach toward feature space analysis. IEEE Trans. on PAMI, 24(5):603--619, May 2002. Google ScholarDigital Library
- S. Dai, M. Han, W. Xu, Y. Wu, and Y. Gong. Soft edge smoothness prior for alpha channel super resolution. In Proc. CVPR, 2007.Google ScholarCross Ref
- R. Fattal. Upsampling via imposed edges statistics. In ACM SIGGRAPH, 2007. Google ScholarDigital Library
- W. Freeman and E. Pasztor. Learning low-level vision. IJCV, 40(1):25--47, 2000. Google ScholarDigital Library
- G. Gilboa, N. A. Sochen, and Y. Y. Zeevi. Regularized shock filters and complex diffusion. Lecture Notes in Computer Science, pages 399--413, 2002. Google ScholarDigital Library
- M. Irani and S. Peleg. Motion analysis for image enhancement: Resolution, occlusion, and transparency. Journal of Visual Communication and Image Representation, 40(4):324--335, 1993.Google ScholarCross Ref
- X. Li and M. Orchard. New edge-directed interpolation.Google Scholar
- Z. Lin, J. He, X. Tang, and C.-K. Tang. Limits of learning-based superresolution algorithms. In Proc. ICCV, 2007.Google ScholarCross Ref
- W. Liu, D. Lin, and X. Tang. Hallucinating faces: Tensorpatch super-resolution and coupled residue compensation. In Proc. CVPR, 2005. Google ScholarDigital Library
- S. Osher and L. I. Rudin. Feature-oriented image enhancement using shock filters. SIAM Journal on Numerical Analysis, 27:919--940, 1990. Google ScholarDigital Library
- Q. Shan, Z. Li, J. Jia, and C.-K. Tang. Fast image/video upsampling. In ACM SIGGRAPH ASIA, 2008. Google ScholarDigital Library
- J. Sun, Z. Xu, and H.-Y. Shum. Image super-resolution using gradient profile prior. In Proc. CVPR, 2008.Google Scholar
- J. Sun, N.-N. Zheng, H. Tao, and H.-Y. Shum. Image hallucination with primal sketch priors. In Proc. CVPR, 2003.Google Scholar
- J. Sun, J. Zhu, and M. Tappen. Context-constrained hallucination for image super-resolution. In Proc. CVPR, 2010.Google ScholarCross Ref
- C. Tomasi and R. Manduchi. Bilateral filtering for gray and color images. In Proc. ICCV, 1998. Google ScholarDigital Library
- Q. Wang, X. Tang, and H. Shum. Patch based blind image super resolution. In Proc. ICCV, 2005. Google ScholarDigital Library
- X. Wang and X. Tang. Hallucinating face by eigentransformation. IEEE Trans. on SMC, Part C, 35(3):425--434, 2005. Google ScholarDigital Library
- Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE Trans. on IP, 13(4):600--612, 2004. Google ScholarDigital Library
- J. Yang, J. Wright, T. Huang, and Y. Ma. Image super-resolution as sparse representation of raw image patches. In Proc. CVPR, 2008.Google Scholar
Index Terms
- Edge-preserving single image super-resolution
Recommendations
Curvature preserving image super-resolution with gradient-consistency-anisotropic-regularization prior
Single image super-resolution (SR) often suffers from annoying interpolation artifacts such as blur, jagged edges, and ringing. In this paper, we aim to achieve artifact-free SR reconstruction from an input low resolution (LR) image using adaptive de-...
Image super-resolution by estimating the enhancement weight of self example and external missing patches
Image super-resolution (SR) is the process of generating a high-resolution (HR) image using one or more low-resolution (LR) inputs. Many SR methods have been proposed, but generating the small-scale structure of an SR image remains a challenging task. ...
Edge-directed single image super-resolution via cross-resolution sharpening function learning
Edge-directed single image super-resolution methods have been paid more attentions due to their sharp edge preserving in the recovered high-resolution image. Their core is the high-resolution gradient estimation. In this paper, we propose a novel cross-...
Comments